Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0790. Min Act: -0.0003

Data Index: 148399 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0003

Data Index: 473667 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0771. Min Act: -0.0003

Data Index: 903697 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0728. Min Act: -0.0003

Data Index: 155524 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1271233 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0700. Min Act: -0.0003

Data Index: 878958 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0698. Min Act: -0.0003

Data Index: 698928 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0678. Min Act: -0.0002

Data Index: 580886 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0669. Min Act: -0.0003

Data Index: 956754 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0663. Min Act: -0.0003

Data Index: 201095 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1211925 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0675. Min Act: -0.0003

Data Index: 355577 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1357797 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0660. Min Act: -0.0003

Data Index: 485741 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0663. Min Act: -0.0003

Data Index: 772243 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0653. Min Act: -0.0003

Data Index: 464103 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1207606 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0658. Min Act: -0.0003

Data Index: 102067 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1322347 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0643. Min Act: -0.0003

Data Index: 328024 (C4 (Web Text))

Max Activating Token Index: 828